Evaluation of landslide disaster susceptibility in Shuangbai County based on random forest modeling

Haoyun Xie

doi:10.62051/ijcsit.v1n1.16

Authors

Haoyun Xie

DOI:

https://doi.org/10.62051/ijcsit.v1n1.16

Keywords:

landslides, Random forest, Susceptibility assessment

Abstract

Shuangbai County, Chuxiong Yi Autonomous Prefecture, Yunnan Province, China, has a high incidence of geohazard events and is a key area for geologic risk prevention and control in China, with landslides accounting for the majority of all geohazard events, so understanding landslide-prone areas in the region is critical to reducing the impacts of landslide hazards. In this study, based on literature reference and background investigation of the study area, relevant data and existing research results were collected, and six types of evaluation factors including elevation, slope, slope direction, rainfall, vegetation type and vegetation index were selected to construct a random forest (RF) model to analyze the landslide susceptibility of Shuangbai County, Chuxiong Prefecture, Yunnan Province, and to obtain the evaluation map of landslide susceptibility in Shuangbai County. The results show that the landslide disaster high susceptibility areas in Shuangbai County are mainly distributed in the northern part of the county in Toudian Township and Dazhuang Township, the southeastern part of Anlongbao Township and the southwestern part of Ejia Township in the vicinity of the Hengduan Mountain Range, which is an important reference for the development of scientific and effective disaster prevention and mitigation strategies, and for the enhancement of the quality of life and the safety of the residents in the area of Shuangbai County.

Downloads

Download data is not yet available.

References

Wu, Z. Study on the genesis factors and susceptibility of landslides and debris flows in Yunnan Province [D]. Beijing: China University of Geosciences, 2016.

HUANG W, DING M, LI Z, et al. An Efficient User-Friendly Integration Tool for Landslide Susceptibility Mapping Based on Support Vector Machines: SVM-LSM Toolbox[J]. Remote Sensing, 2022, 14(14): 3408.

SHARMA A, PRAKASH C, MANIVASAGAM V S. Entropy-Based Hybrid Integration of Random Forest and Support Vector Machine for Landslide Susceptibility Analysis[J]. Geomatics, 2021, 1(4): 399-416.

BREIMAN L. Random Forests[J]. Machine Learning, 2001, 45(1): 5-32.

GANAIE M A, TANVEER M, SUGANTHAN P N, et al. Oblique and rotation double random forest[J]. Neural networks : the official journal of the International Neural Network Society, 2022, 153: 496-517.

Li, J., Wang, H., Wang, R. Landslide Susceptibility Assessment in Fuzhou Area Based on Machine Learning Models[J]. Journal of Water Resources and Architectural Engineering, 2022, 20(02), 146-152.